Back to skill

Security audit

GrowSurf

Security checks for vulnerabilities and agentic risk

Overview

GrowSurf changes require user approval, but missing-tool setup directs execution of unverified remote installers without a separate approval step.

Review and approve CLI installation separately, using a verified, pinned release. Check its automatic agent-skill installation behavior and connect only the intended GrowSurf account. Retain the required approvals for writes and deletions. Remote installer contents and hosted connector implementations could not be verified.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code performs remote script execution and contains no GrowSurf integration or data operations. Dependency installation could be a supporting implementation detail, but the supplied content establishes no relationship between this installer and GrowSurf. The downloaded script's further behavior is not visible.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an HTTPS download directly into Bash executes mutable remote content without a pinned version or independent integrity verification; the PowerShell alternative has the same weakness. Compromise of the installer endpoint or its publishing pipeline could lead to code execution, local credential theft, or file modification with the agent's privileges, although the supplied content does not establish that the endpoint is malicious.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

Fallback setup executes downloaded installer scripts without warning about system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback directs the agent to execute a remotely supplied installer without requiring user approval for local software installation or explaining its system effects. Restricting this to a missing-CLI error reduces exposure, but a GrowSurf data request does not itself authorize arbitrary installation code to run with the agent's local privileges.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 85)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources